8.3 Dynamic Thermal Management for Multi-cores

Printer-friendly version PDF version

Date: Wednesday 11 March 2015
Time: 17:00 - 18:30
Location / Room: Stendhal

Chair:
Georgios Karakonstantis, Queen's University, GB

Co-Chair:
José Luis Ayala, Complutense University of Madrid, ES

This session covers the state-of-the-art in dynamic thermal management techniques for multi-core platforms in the mobile and high-performance computing domains. The issues addressed include thermal stress, thermal modeling and emerging cooling solutions.

TimeLabelPresentation Title
Authors
17:008.3.1A THERMAL STRESS-AWARE ALGORITHM FOR POWER AND TEMPERATURE MANAGEMENT OF MPSOCS
Speakers:
Mehdi Kamal1, Arman Iranfar1, Ali Afzali-Kusha1 and Massoud Pedram2
1University of Tehran, IR; 2University of Southern California, US
Abstract
In this work, we propose a thermal stress-aware algorithm for the management of the power and temperature in MPSoCs. The algorithm, which uses a heuristic approach, controls the power consumption, maximum temperature, thermal cycles, and temporal/spatial thermal gradients of MPSoCs. At the top level, the decision on turning the cores on and off is made based on the constraints of peak temperature, maximum spatial thermal gradients, and power consumption. At the next tier,the optimal frequencies (and supply voltages) of the ON cores, formulated in a convex optimization problem, are determined again based on satisfying the constraints of the maximum total power consumption, peak temperature, thermal cycles, and also temporal thermal gradients. The technique may be applied to both the heterogeneous and homogenous MPSoCs. The efficacy of the proposed approach in reducing the thermal cycles as well as temporal thermal gradients is evaluated by comparing its results with a similar previous power and temperature management approach. The evaluation which is performed on 8-core processors under Splash2 benchmarks, demonstrates the ability of the suggested technique in limiting a considerable reduction in the thermal stress parameters.

Download Paper (PDF; Only available from the DATE venue WiFi)
17:308.3.2PREDICTIVE DYNAMIC THERMAL AND POWER MANAGEMENT FOR HETEROGENEOUS MOBILE PLATFORMS
Speakers:
Gaurav Singla1, Gurinderjit Kaur1, Ali Unver2 and Umit Y Ogras1
1Arizona State University, US; 2Intel Corporation, US
Abstract
Heterogeneous multiprocessor system-on-chip (MPSoCs) powering mobile platforms integrate multiple asymmetric CPU cores, GPU, and many specialized processors. When the MPSoC operates close to its peak performance, power dissipation easily increases the temperature, hence adversely impacts reliability. Since using a fan is not a viable solution for hand-held devices, there is a strong need for dynamic thermal and power management (DTPM) algorithms that can regulate temperature with minimal performance impact. This paper presents a DTPM algorithm based on a practical temperature prediction methodology using system identification. The DTPM algorithm dynamically computes a power budget using the predicted temperature, and controls the types and number of active processors as well as their frequencies. Experiments on an octa-core big.LITTLE processor and common Android apps demonstrate that the proposed technique predicts temperature within 3% accuracy, while the DTPM algorithm provides around 6x reduction in temperature variance, and as large as 16% reduction in total platform power compared to using a fan.

Download Paper (PDF; Only available from the DATE venue WiFi)
18:008.3.3POWER-EFFICIENT CONTROL OF THERMOELECTRIC COOLERS CONSIDERING DISTRIBUTED HOT SPOTS
Speakers:
Mohammad Javad Dousti and Massoud Pedram, University of Southern California, US
Abstract
Thermoelectric coolers are compact devices that can target hot spots on a VLSI die. These devices are connected electrically in series and controlled together, i.e., all are ON or OFF at the same time. However, spatial and temporal distributions of hot spots on a VLSI die are non-uniform, and therefore, activating all of TECs to address one or a few localized hot spots is not economical. This traditional technique indeed leads to a significant power waste. This paper suggests that adjacent hot spots with the same thermal behavior can be grouped and controlled by a cluster of TECs. A bypass switch for each TEC cluster is added in order to allow selectively turning OFF some TEC clusters which are needed. More precisely, a clustering problem is formulated which aims to minimize the power waste due to excessive use of TECs. Due to the large number of variables in problems of interesting sizes, a greedy heuristic method for solving the problem is introduced. It is shown that the proposed heuristic can reduce the wasted power on average by 81% and also decrease the total TEC power consumption on average by 42%.

Download Paper (PDF; Only available from the DATE venue WiFi)
18:30IP4-3, 148USER-SPECIFIC SKIN TEMPERATURE-AWARE DVFS FOR SMARTPHONES
Speakers:
Begum Birsen Egilmez1, Gokhan Memik1, Seda Ogrenci-Memik1 and Oğuz Ergin2
1Northwestern University, US; 2TOBB University of Economics and Technology, TR
Abstract
Skin temperature of mobile devices intimately affects the user experience. Power management schemes built into smartphones can lead to quickly crossing a user's threshold of tolerable skin temperature. Furthermore, there is a significant variation among users in terms of their sensitivity. Hence, controlling the skin temperature as part of the device's power management scheme is paramount. To achieve this, we first present a method for estimating skin and screen temperature at run-time using a combination of available on-device thermal sensors and performance indicators. In an Android-based smartphone, we achieve 99.05% and 99.14% accuracy in estimations of back cover and screen temperatures, respectively. Leveraging this run-time predictor, we develop User-specific Skin Temperature-Aware (USTA) DVFS mechanism to control the skin temperature. Performance of USTA is tested both with benchmarks and user tests comparing USTA to the standard Android governor. The results show that more users prefer to use USTA as opposed to the default DVFS mechanism.

Download Paper (PDF; Only available from the DATE venue WiFi)
18:31IP4-4, 503FORMAL PROBABILISTIC ANALYSIS OF DISTRIBUTED DYNAMIC THERMAL MANAGEMENT
Speaker:
Muhammad Shafique, Karlsruhe Institute of Technology (KIT), DE
Authors:
Shafaq Iqtedar1, Osman Hasan2, Muhammad Shafique3 and Joerg Henkel3
1National University of Sciences and Technology (NUST), Islamabad, PK; 2National University of Sciences and Technology (NUST), Islamabad, ; 3Karlsruhe Institute of Technology (KIT), DE
Abstract
The prevalence of Dynamic Thermal Management (DTM) schemes coupled with demands for high reliability motivate the rigorous verification and testing of these schemes before deployment. Conventionally, these schemes are analyzed using either simulations or by running on real systems. But these traditional analysis techniques cannot exhaustively validate the distributed DTM schemes and thus compromise on the accuracy of the analysis results. Moreover, the randomness due to task assignments, task completion times and re-mappings, is often ignored in the analysis of distributed DTM schemes. We propose to overcome both of these limitations by using probabilistic model checking, which is a formal method for modeling and verifying concurrent systems with randomized behaviors. The paper presents a case study on the formal verification of a state-ofthe- art distributed DTM scheme using the PRISM model checker.

Download Paper (PDF; Only available from the DATE venue WiFi)
18:30End of session
19:30DATE Party in Museum of Grenoble (Musée de Grenoble, 5 Place de Lavalette, 38000 Grenoble, France)

Musée de Grenoble

As one of the main networking opportunities during the DATE week, the DATE Party states a perfect occasion to meet friends and colleagues in a relaxed atmosphere while enjoying local amenities. It will take place on March 11, 2015, from 19:30 to 23:00 in the renowned "Musée de Grenoble" (Grenoble Museum). This painting museum features a unique collection of ancient, modern and contemporary art including major masterpieces of classical Flemish, Dutch, Italian and Spanish painting and all the great pot-1945 contemporary art-trends, right up to the most recent artwork of the 2000s.

During this evening, you can enjoy the famous French Cuisine and outstanding wines. Discover the region of the French Alps through ist cheese and wine specialties. The dinner will be accompanied by jazz songs and instrumental music from Anna Cruz and her vocal band. Another highlight will be the show waders "THE INSEPARABLES", sweet and ephemeral characters walking through the premises, releasing dreams and laughter. Furthermore, at the very beginning of the evening, from 20h00 to 21h30, you will have the opportunity to visit parts of the permanent collection of the museum (ninetieth and twenties century).

Please kindly note that it is not a seated dinner.

All delegates, exhibitors and their guests are invited to attend the party. Please be aware that entrance is only possible with a valid party ticket. Each full conference registration includes a ticket for the DATE Party (which needs to be booked during the online registration process though). Additional tickets can be purchased on-site at the registration desk (subject to availability of tickets). Price for extra ticket: 60 € per person.

How to get there: The tram B has a stop called "Notre Dame Musee". That stop is next to the Museum. Attendees would take the tram A from Alpexpo and change for Tram B in one of the stations between "Gares" and "Maison du Tourisme" to get to the museum. The trip takes about 30 minutes.